DEV Community

Cover image for Don’t let AI break your collective thinking: a practical guide for engineering teams

Don’t let AI break your collective thinking: a practical guide for engineering teams

Julien Avezou on May 25, 2026

Over the past few years, my workflow as an engineer has changed a lot. I went from the occasional autocomplete to using AI for ideation, debugging...
Collapse
 
itskondrat profile image
Mykola Kondratiuk

individual gains are obvious but team costs are subtle - that's what makes them dangerous to catch. in my experience the tell is whether teammates can still explain their decisions to each other, or just say 'AI suggested it.'

Collapse
 
javz profile image
Julien Avezou

team knowledge sharing remains core I agree

Collapse
 
itskondrat profile image
Mykola Kondratiuk

yeah and the gap between "i know how this agent works" and "anyone on my team could debug it" is wider than most people track until someone goes on leave

Collapse
 
itsugo profile image
Aryan Choudhary

It seems to me that you've really stumbled upon something profound here. The more we rely on AI, the more we risk losing sight of what makes us a team in the first place - our shared humanity. I love that he's proposing these practical exercises, like building a shared mental model, to keep our feet on the ground. It's such a simple yet vital reminder that AI is just a tool, not a replacement for the messy beauty of collaboration. Great Post Julien!

Collapse
 
javz profile image
Julien Avezou

Thanks Aryan!

Collapse
 
capestart profile image
CapeStart

AI scales output. Teams still need to scale understanding.

Collapse
 
javz profile image
Julien Avezou

100%

Collapse
 
atatatko profile image
Yurii Cherkasov • Edited

One very practical solution (that I also work on now) is to stop treating AI conversations as disposable personal artifacts of the team members.

Many useful things happen inside AI-assisted workflows. Let's say, developer investigates a rendering bug. AI suggests several possible causes - the engineer rejects some, verifies one, a workaround or real fix is found.

The entire logical chain disappears inside a private chat window.

That is lost team memory.

A possible solution is to collect selected AI-assisted work into a shared searchable store: PostgreSQL + pgvector, or a dedicated vector database.

The goal is not to store every token forever, but to preserve useful engineering context - for that the context should be analyzed and compress into a useful informational artifact:

  • Who worked on it?
  • When?
  • What system/component was involved?
  • What was the problem?
  • What hypotheses were explored?
  • What was verified manually?
  • What was the final solution?
  • What should the team remember?

Including links to the ticket, PR, annotated commits history, logs

Then the team can ask questions like:

Something was discussed in May about rendering flicker on Intel GPUs. Who worked on it, what was the cause, and how did we fix it?

This effectively turns AI output from private productivity pieces into a collective team memory.

Collapse
 
javz profile image
Julien Avezou

I like that idea and framing. Thanks for sharing this.

Collapse
 
mudassirworks profile image
Mudassir Khan

the 'AI usage in PR template' practice is one of those things that sounds like overhead until you realize your team has been debug fixing AI code for months without anyone knowing where the shortcuts were taken.

we added a similar note to our internal reviews. the pattern that emerged: AI was being used most in the parts of the codebase nobody wanted to touch. the less understood the module, the more AI assistance, the more drift. circular.

the 'debugging without AI, narrated aloud' session is the one i'd actually steal. curious: do you record those, or is the value mostly in the live observation?

Collapse
 
javz profile image
Julien Avezou

You can host a live session with your team and use it as a knowledge sharing session while collectively debugging. If you can record it that's even better, and get a transcript so you can use it as context for future tooling if beneficial.

Collapse
 
coridev profile image
Cor E

This is really good. Just stopping to ask some of those critical questions makes you think more like an engineer.

Collapse
 
javz profile image
Julien Avezou

Exactly. Are there particular critical questions that have helped you as an engineer?

Collapse
 
coridev profile image
Cor E

Let's just say I've learned to question outputs in detail. :D I like your ideas though and will definitely give them some more consideration.

Collapse
 
monom profile image
Rasmus Ros

Having the PR template include a section on how AI was used is great. I'm gonna implement this with my team!

Collapse
 
javz profile image
Julien Avezou

Happy this post inspired you Rasmus. Sounds great!
It's a little added friction but that can compound into very useful insights over time.